{"total":287,"rows":[{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2410.10813","title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","created":"2024-10-14","cited_by_count":707,"area":null},{"id":"2310.06839","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","created":"2023-10-10","cited_by_count":453,"area":"inference"},{"id":"2502.11089","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","created":"2025-02-16","cited_by_count":407,"area":null},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383,"area":null},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246,"area":"lr"},{"id":"2310.16427","title":"PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization","created":"2023-10-25","cited_by_count":233,"area":null},{"id":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223,"area":"inference"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2310.07240","title":"CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving","created":"2023-10-11","cited_by_count":203,"area":"inference"},{"id":"2412.13171","title":"Compressed Chain of Thought: Efficient Reasoning Through Dense Representations","created":"2024-12-17","cited_by_count":201,"area":"lr"},{"id":"2405.13576","title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","created":"2024-05-22","cited_by_count":166,"area":"mllm"},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128,"area":null},{"id":"2502.05589","title":"On Memory Construction and Retrieval for Personalized Conversational Agents","created":"2025-02-08","cited_by_count":105,"area":"rag"},{"id":"2401.03462","title":"Long Context Compression with Activation Beacon","created":"2024-01-07","cited_by_count":104,"area":"inference"},{"id":"2406.13629","title":"InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales","created":"2024-06-19","cited_by_count":101,"area":"rag"},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2404.15146","title":"Rethinking LLM Memorization through the Lens of Adversarial Compression","created":"2024-04-23","cited_by_count":94,"area":"lr"},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"area":null},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"id":"2407.01219","title":"Searching for Best Practices in Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":83,"area":"rag"},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2410.14052","title":"From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs","created":"2024-10-17","cited_by_count":79,"area":null},{"id":"2402.02244","title":"Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models","created":"2024-02-03","cited_by_count":76,"area":"lr"},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2407.14057","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","created":"2024-07-19","cited_by_count":70,"area":"inference"},{"id":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66,"area":"rag"},{"id":"2502.00299","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","created":"2025-02-01","cited_by_count":60,"area":"inference"},{"id":"2406.15334","title":"Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning","created":"2024-06-21","cited_by_count":50,"area":"mllm"},{"id":"2505.18227","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","created":"2025-05-23","cited_by_count":50,"area":"inference"},{"id":"2406.14528","title":"DeciMamba: Exploring the Length Extrapolation Potential of Mamba","created":"2024-06-20","cited_by_count":49,"area":"ssm"},{"id":"2404.12096","title":"LongEmbed: Extending Embedding Models for Long Context Retrieval","created":"2024-04-18","cited_by_count":48,"area":null},{"id":"2404.01077","title":"Efficient Prompting Methods for Large Language Models: A Survey","created":"2024-04-01","cited_by_count":47,"area":null},{"id":"2601.16746","title":"SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents","created":"2026-01-23","cited_by_count":44,"area":"agents"},{"id":"2510.00446","title":"LongCodeZip: Compress Long Context for Code Language Models","created":"2025-10-01","cited_by_count":39,"area":null},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2503.14337","title":"PENCIL: Long Thoughts with Short Memory","created":"2025-03-18","cited_by_count":33,"area":"lr"},{"id":"2410.02338","title":"How Much Can RAG Help the Reasoning of LLM?","created":"2024-10-03","cited_by_count":31,"area":"lr"},{"id":"2404.15500","title":"GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilots","created":"2024-04-23","cited_by_count":30,"area":null},{"id":"2410.03227","title":"ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering","created":"2024-10-04","cited_by_count":26,"area":"lr"},{"id":"2405.16178","title":"Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection","created":"2024-05-25","cited_by_count":25,"area":"rag"},{"id":"2410.03065","title":"Compute Or Load KV Cache? Why Not Both?","created":"2024-10-04","cited_by_count":25,"area":"inference"},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2510.05069","title":"SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs","created":"2025-10-06","cited_by_count":22,"area":"lr"},{"id":"2502.00791","title":"Vision-centric Token Compression in Large Language Model","created":"2025-02-02","cited_by_count":21,"area":"inference"},{"id":"2505.14827","title":"Text Generation Beyond Discrete Token Sampling","created":"2025-05-20","cited_by_count":21,"area":null},{"id":"2601.13879","title":"Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring","created":"2026-01-20","cited_by_count":21,"area":"lr"},{"id":"2406.14848","title":"Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models","created":"2024-06-21","cited_by_count":20,"area":null},{"id":"2407.15504","title":"Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models","created":"2024-07-22","cited_by_count":19,"area":"inference"},{"id":"2404.00489","title":"Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression","created":"2024-03-30","cited_by_count":18,"area":"inference"},{"id":"2508.04664","title":"Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management","created":"2025-08-06","cited_by_count":18,"area":null},{"id":"2403.09192","title":"PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation","created":"2024-03-14","cited_by_count":17,"area":null},{"id":"2409.13761","title":"Do Large Language Models Need a Content Delivery Network?","created":"2024-09-16","cited_by_count":16,"area":"inference"},{"id":"2509.25651","title":"AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation","created":"2025-09-30","cited_by_count":15,"area":null},{"id":"2604.19572","title":"A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression","created":"2026-04-21","cited_by_count":15,"area":"inference"},{"id":"2606.28434","title":"SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents","created":"2026-06-26","cited_by_count":15,"area":"agents"},{"id":"2409.05152","title":"OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs","created":"2024-09-08","cited_by_count":14,"area":null},{"id":"2507.08944","title":"Optimizing Sequential Multi-Step Tasks with Parallel LLM Agents","created":"2025-07-11","cited_by_count":14,"area":"agents"},{"id":"2604.01664","title":"ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents","created":"2026-04-02","cited_by_count":14,"area":"agents"},{"id":"2607.05378","title":"CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents","created":"2026-07-06","cited_by_count":14,"area":"lr"},{"id":"2409.06679","title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","created":"2024-09-10","cited_by_count":13,"area":"lr"},{"id":"2410.04698","title":"MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs","created":"2024-10-07","cited_by_count":13,"area":"lr"},{"id":"2506.12707","title":"SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression","created":"2025-06-15","cited_by_count":13,"area":"inference"},{"id":"2407.14192","title":"LeKUBE: A Legal Knowledge Update BEnchmark","created":"2024-07-19","cited_by_count":12,"area":null},{"id":"2410.05801","title":"Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation","created":"2024-10-08","cited_by_count":12,"area":"lr"},{"id":"2501.12959","title":"Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference","created":"2025-01-22","cited_by_count":12,"area":"inference"},{"id":"2505.22662","title":"AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models","created":"2025-05-28","cited_by_count":12,"area":"lr"},{"id":"2410.08391","title":"KV Prediction for Improved Time to First Token","created":"2024-10-10","cited_by_count":11,"area":"inference"},{"id":"2406.13399","title":"VELO: A Vector Database-Assisted Cloud-Edge Collaborative LLM QoS Optimization Framework","created":"2024-06-19","cited_by_count":10,"area":null},{"id":"2409.15895","title":"Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation","created":"2024-09-24","cited_by_count":10,"area":"rag"},{"id":"2507.05633","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","created":"2025-07-08","cited_by_count":10,"area":"rag"},{"id":"2509.13723","title":"DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning","created":"2025-09-17","cited_by_count":10,"area":"lr"},{"id":"2512.14946","title":"EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving","created":"2025-12-16","cited_by_count":10,"area":"inference"},{"id":"2608.06503","title":"Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability","created":"2026-08-06","cited_by_count":10,"area":"inference"},{"id":"2410.10074","title":"Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2503.15191","title":"Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems","created":"2025-03-19","cited_by_count":9,"area":"rag"},{"id":"2509.01092","title":"REFRAG: Rethinking RAG based Decoding","created":"2025-09-01","cited_by_count":9,"area":"lr"},{"id":"2603.19595","title":"All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution","created":"2026-03-20","cited_by_count":9,"area":"agents"},{"id":"2604.02985","title":"Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference","created":"2026-04-03","cited_by_count":9,"area":"rag"},{"id":"2505.00019","title":"An Empirical Study on Prompt Compression for Large Language Models","created":"2025-04-24","cited_by_count":8,"area":"inference"},{"id":"2508.20368","title":"AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning","created":"2025-08-28","cited_by_count":8,"area":"agents"},{"id":"2509.23873","title":"Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":8,"area":"alignment"},{"id":"2510.16786","title":"More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents","created":"2025-10-19","cited_by_count":8,"area":"agents"},{"id":"2401.07793","title":"Flexibly Scaling Large Language Models Contexts Through Extensible Tokenization","created":"2024-01-15","cited_by_count":7,"area":"rag"},{"id":"2405.18272","title":"Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2408.00274","title":"QUITO: Accelerating Long-Context Reasoning through Query-Guided Context Compression","created":"2024-08-01","cited_by_count":7,"area":"lr"},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2503.01425","title":"MeshPad: Interactive Sketch-Conditioned Artist-Reminiscent Mesh Generation and Editing","created":"2025-03-03","cited_by_count":7,"area":null},{"id":"2510.20797","title":"No Mean Feat: Simple, Strong Baselines for Context Compression","created":"2025-10-23","cited_by_count":7,"area":"inference"},{"id":"2511.05385","title":"TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework","created":"2025-11-07","cited_by_count":7,"area":"lr"},{"id":"2606.25449","title":"Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One","created":"2026-06-24","cited_by_count":7,"area":null},{"id":"2401.09486","title":"LoMA: Lossless Compressed Memory Attention","created":"2024-01-16","cited_by_count":6,"area":"inference"},{"id":"2404.17897","title":"Tool Calling: Enhancing Medication Consultation via Retrieval-Augmented Large Language Models","created":"2024-04-27","cited_by_count":6,"area":"rag"},{"id":"2409.15699","title":"Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation","created":"2024-09-24","cited_by_count":6,"area":"rag"},{"id":"2410.13073","title":"PromptExp: Multi-granularity Prompt Explanation of Large Language Models","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2412.09919","title":"B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens","created":"2024-12-13","cited_by_count":6,"area":"inference"},{"id":"2501.02552","title":"Multi-LLM Collaborative Caption Generation in Scientific Documents","created":"2025-01-05","cited_by_count":6,"area":null}],"next_cursor":"100"}